# Introduction

***

## What are MCP?

The Model Context Protocol is a new standard for connecting AI Agents to external tools. Learn more about MCP here <https://www.anthropic.com/news/model-context-protocol><br>

***

## What's the Katoshi MCP?

The Katoshi MCP allows you to build AI Agents that have the ability to execute trades on your linked Hyperliquid accounts. It is a "toolbox" that your agents can use as per your instructions.&#x20;

For example, agents can fetch your open positions, get the latest price of any asset, open/close positions, and more [Tools](/katoshi-docs/mcp/tools.md) to come. <br>

***

## What can I build with this?

Using tools like [n8n](/katoshi-docs/mcp/quickstart.md#n8n) that offers user-friendly agent builder flows, you can create complex AI Agents that analyze the market, evaluate the sentiment on Twitter/X, scrape any web data, get the current moon cycle, execute trades only if X condition is met, and so much more! \
\
You can also connect our MCP server to AI chat clients like Claude Desktop, to use as a trading assistant.

Simply give your instructions as a prompt to you agent, then connect external tools via MCPs.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://katoshi.gitbook.io/katoshi-docs/mcp/introduction.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.